Efficient multi-agent communication via self-supervised information aggregation
Utilizing messages from teammates can improve coordination in cooperative Multi-agent
Reinforcement Learning (MARL). To obtain meaningful information for decision-making …
Reinforcement Learning (MARL). To obtain meaningful information for decision-making …
What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?
Various methods for Multi-Agent Reinforcement Learning (MARL) have been developed
with the assumption that agents' policies are based on accurate state information. However …
with the assumption that agents' policies are based on accurate state information. However …
Security and Privacy Issues in Deep Reinforcement Learning: Threats and Countermeasures
Deep Reinforcement Learning (DRL) is an essential subfield of Artificial Intelligence (AI),
where agents interact with environments to learn policies for solving complex tasks. In recent …
where agents interact with environments to learn policies for solving complex tasks. In recent …
Certified policy smoothing for cooperative multi-agent reinforcement learning
Cooperative multi-agent reinforcement learning (c-MARL) is widely applied in safety-critical
scenarios, thus the analysis of robustness for c-MARL models is profoundly important …
scenarios, thus the analysis of robustness for c-MARL models is profoundly important …
Instructed diffuser with temporal condition guidance for offline reinforcement learning
Recent works have shown the potential of diffusion models in computer vision and natural
language processing. Apart from the classical supervised learning fields, diffusion models …
language processing. Apart from the classical supervised learning fields, diffusion models …
Robust cooperative multi-agent reinforcement learning via multi-view message certification
Many multi-agent scenarios require message sharing among agents to promote
coordination, hastening the robustness of multi-agent communication when policies are …
coordination, hastening the robustness of multi-agent communication when policies are …
Optimal Cost Constrained Adversarial Attacks for Multiple Agent Systems
Since many security-related applications use multi-agent reinforcement learning as their
underlying algorithms, the study on the adversarial attacks against mutli-agent reinforcement …
underlying algorithms, the study on the adversarial attacks against mutli-agent reinforcement …
Robust Multi-agent Communication via Multi-view Message Certification
Many multi-agent scenarios require message sharing among agents to promote
coordination, hastening the robustness of multi-agent communication when policies are …
coordination, hastening the robustness of multi-agent communication when policies are …
Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
Most existing works focus on direct perturbations to the victim's state/action or the underlying
transition dynamics to demonstrate the vulnerability of reinforcement learning agents to …
transition dynamics to demonstrate the vulnerability of reinforcement learning agents to …
[PDF][PDF] Towards Robust and Adaptable Real-World Decision Making Systems
Y Sun - ycsun2017.github.io
Empowered by high-performance computing techniques and large volumes of datasets,
machine learning (ML) has achieved significant and rapid development in a wide range of …
machine learning (ML) has achieved significant and rapid development in a wide range of …